# Cocktail Edge Caching: Ride Dynamic Trends of Content Popularity with Ensemble Learning

arXiv: https://arxiv.org/abs/2101.05885 · HTML: https://mlsanity.com/paper/2101.05885/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 46 references that are in the map.
- First posted on arXiv 14 Jan 2021.

## Builds on (most cited first, 10 of 10)

- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Optimal and Scalable Caching for 5G Using Reinforcement Learning of Space-time Popularities](https://mlsanity.com/paper/1708.06698/) (2017)
- [A Reinforcement-Learning Approach to Proactive Caching in Wireless Networks](https://mlsanity.com/paper/1712.07084/) (2017)
- [Temporal Locality in Today's Content Caching: Why it Matters and How to Model it](https://mlsanity.com/paper/1305.7114/) (2013)
- [A Survey on Mobile Edge Networks: Convergence of Computing, Caching and Communications](https://mlsanity.com/paper/1703.10750/) (2017)
- [Reinforcement Learning for Adaptive Caching with Dynamic Storage Pricing](https://mlsanity.com/paper/1812.08593/) (2018)
- [Understanding Performance of Edge Content Caching for Mobile Video Streaming](https://mlsanity.com/paper/1702.07627/) (2017)
- [Unravelling the Impact of Temporal and Geographical Locality in Content Caching Systems](https://mlsanity.com/paper/1501.03354/) (2015)
- [Accurate Learning or Fast Mixing? Dynamic Adaptability of Caching Algorithms](https://mlsanity.com/paper/1701.02214/) (2017)
- [PA-Cache: Evolving Learning-Based Popularity-Aware Content Caching in Edge Networks](https://mlsanity.com/paper/2002.08805/) (2020)

## Built on by (most cited first, 5 of 5)

- [Predictive Edge Caching through Deep Mining of Sequential Patterns in User Content Retrievals](https://mlsanity.com/paper/2210.02657/) (2022)
- [Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis](https://mlsanity.com/paper/2408.05635/) (2024)
- [Semantics-enhanced Temporal Graph Networks for Content Popularity Prediction](https://mlsanity.com/paper/2301.12355/) (2023)
- [Edge Caching Optimization with PPO and Transfer Learning for Dynamic Environments](https://mlsanity.com/paper/2411.09812/) (2024)
- [Spatial Visibility and Temporal Dynamics: Revolutionizing Field of View Prediction in Adaptive Point Cloud Video Streaming](https://mlsanity.com/paper/2409.18236/) (2024)

## Abstract (arXiv)

Edge caching will play a critical role in facilitating the emerging content-rich applications. However, it faces many new challenges, in particular, the highly dynamic content popularity and the heterogeneous caching configurations. In this paper, we propose Cocktail Edge Caching, that tackles the dynamic popularity and heterogeneity through ensemble learning. Instead of trying to find a single dominating caching policy for all the caching scenarios, we employ an ensemble of constituent caching policies and adaptively select the best-performing policy to control the cache. Towards this goal, we first show through formal analysis and experiments that different variations of the LFU and LRU policies have complementary performance in different caching scenarios. We further develop a novel caching algorithm that enhances LFU/LRU with deep recurrent neural network (LSTM) based time-series analysis. Finally, we develop a deep reinforcement learning agent that adaptively combines base caching policies according to their virtual hit ratios on parallel virtual caches. Through extensive experiments driven by real content requests from two large video streaming platforms, we demonstrate that CEC not only consistently outperforms all single policies, but also improves the robustness of them. CEC can be well generalized to different caching scenarios with low computation overheads for deployment.